Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
INTRA: Interleaved Non-contiguous Token spaRse Attention
Yuxuan Xia, Wenbo Lu, Shaoyi Zheng +1
Transformers achieve strong performance across modalities but are bottlenecked by the quadratic cost of attention. Sparse attention can reduce this cost, but effective sparsity mus…
cs.LG2026
Smoothing Dark Areas in Molecular Latent Diffusion
Xi Wang, Jiahan Li, Yuxuan Xia +3
Latent diffusion is a promising framework for scalable 3D molecular generation, but it requires a latent space that remains smooth, valid, and navigable beyond posterior samples. E…
cs.LG2025
ToMA: Token Merge with Attention for Diffusion Models
Wenbo Lu, Shaoyi Zheng, Yuxuan Xia +1
Diffusion models excel in high-fidelity image generation but face scalability limits due to transformers' quadratic attention complexity. Plug-and-play token reduction methods like…